Prostate Cancer

Prostate cancer is a common cancer with significant implications for global health. Prompt and precise identification is crucial for efficient treatment strategizing and enhanced patient results. This research study investigates the utilization of machine learning techniques to diagnose prostate cancer. It emphasizes utilizing deep learning models, namely VGG16, VGG19, ResNet50, and ResNet50V2, to extract relevant features. The random forest approach then uses these features for classification. The study begins by doing a thorough comparison examination of the deep learning architectures outlined above to evaluate their effectiveness in extracting significant characteristics from prostate cancer imaging data. Key metrics such as sensitivity, specificity, and accuracy are used to assess the models’ efficacy. With an accuracy of 99.64%, ResNet50 outperformed other tested models when it came to identifying important features in images of prostate cancer. Furthermore, the analysis of understanding factors aims to offer valuable insights into the decision-making process, thereby addressing a critical problem for clinical practice acceptance. The random forest classifier, a powerful ensemble learning method renowned for its adaptability and ability to handle intricate datasets, then uses the collected characteristics as input. The random forest model seeks to identify patterns in the feature space and produce precise predictions on the presence or absence of prostate cancer. In addition, the study tackles the restricted availability of datasets by utilizing transfer learning methods to refine the deep learning models using a small amount of annotated prostate cancer data. The objective of this method is to improve the ability of the models to generalize across different patient populations and clinical situations. This study’s results are useful because they show how well VGG16, VGG19, ResNet50, and ResNet50V2 work for extracting features in the field of diagnosing prostate cancer, when used with random forest’s classification abilities. The results of this work provide a basis for creating reliable and easily understandable machine learning-based diagnostic tools for detecting prostate cancer. This will enhance the possibility of an early and precise diagnosis in clinical settings such as index terms deep learning, machine learning, prostate cancer, cancer identification, and cancer classification.

The aim of the study was to compare the side effects of high-dose-rate brachytherapy (HDRBT) and low-dose-rate brachytherapy (LDRBT), with a particular focus on the effects on sexual functions and sexual well-being (PROMOBRA study, NCT02258087). Localized low-risk and low-intermediate-risk prostate cancer patients were treated with mono LDR (N = 123, 145 Gy dose) or mono HDR brachytherapy (N = 117, 19/21 Gy). Prior to the treatment and during follow-up (at 3, 6, 9, 12, 18, and 24 months after treatment, and then annually after two years), patients completed patient-reported outcome measurement (PROM) questionnaires EORTC QLQ-PR-25, International Index of Erectile Function (IIEF), and IIEF-5 (SHIM). We compared the patients in different group breakdowns (HDR vs. LDR, hormone naïve and hormone-receiving HDR vs. LDR, hormone naïve and hormone-receiving patients in general, and 19 Gy HDR vs. 21 Gy HDR). In the hormone-naive LDR group, erectile function, orgasm function, sexual desire, satisfaction with intercourse, and overall satisfaction functions significantly decreased compared to baseline throughout the whole follow-up period. However, there were significant decreases in function at a maximum of three time points after HDR therapy without hormone therapy. In hormone-receiving patients, the orgasm function was significantly better in the HDR group at multiple time points compared to the baseline, and sexual desire improved at four time points. According to our results, both LDRBT and HDRBT can be safely administered to patients with localized prostate cancer. In hormone-naive patients, the HDR group showed only recovering decreases in sexual functions, while the LDR group showed a lasting decline in multiple areas. Thus, HDR appears to be more advantageous to hormone-naive patients.

Prostate cancer (PCa) stage at diagnosis is an important predictor of cancer prognosis. In Canada, over one-quarter of males are diagnosed with advanced-stage PCa. Studies have identified several factors associated with PCa stage at diagnosis; however, evidence from Canada is limited. This study aimed to examine associations between sociodemographic characteristics, health history, health practices, and psychosocial factors and PCa stage at diagnosis among males participating in Alberta’s Tomorrow Project (ATP), a prospective cohort in Alberta, Canada. The study included males aged 35–69 years who developed PCa until January 2018. Factors associated with PCa stage at diagnosis were examined using partial proportional odds (PPO) ordinal regression models. A total of 410 males were diagnosed with PCa over the study period. A higher number of lifetime prostate-specific antigen tests were associated with earlier-stage PCa (OR 0.91,  = 0.02, 95% CI 0.83–0.99), while higher abdominal circumference (OR 1.02,  = 0.05, 95% CI 1.00–1.03), lower social support (OR 2.34,  < 0.01, 95% CI 1.31–4.17), and having children (OR 2.67,  < 0.01, 95% CI 1.38–5.16) were associated with later-stage disease. This study identified factors previously found in the literature as well as novel factors associated with PCa stage at diagnosis, which can help inform targets for cancer prevention programs to improve PCa prognosis.

Background. Androgen deprivation therapy (ADT) for prostate cancer is implicated as a possible cause of cognitive impairment (CI). CI in dementia and Alzheimer’s disease is associated with neuroinflammation. In this study, we investigated a potential role of neuroinflammation in ADT-related CI. Methods. Patients with prostate cancer on ADT for ≥3 months were categorized as having ADT-emergent CI or normal cognition (NC) based on self-report at interview. Neuroinflammation was evaluated using positron emission tomography (PET) with the translocator protein (TSPO) radioligand [¹¹C]-PBR28. [¹¹C]-PBR28 uptake in various brain regions was quantified as standardized uptake value (SUVR, normalized to cerebellum) and related to blood oxygen level-dependent functional magnetic resonance imaging (BOLD-fMRI) choice-reaction time task (CRT) activation maps. Results. Eleven patients underwent PET: four with reported CI (rCI), six with reported NC (rNC), and one status unrecorded. PET did not reveal any between-group differences in SUVR regionally or globally. There was no difference between groups on brain activation to the CRT. Regardless of the reported cognitive status, there was strong correlation between PET-TSPO signal and CRT activation in the hippocampus, amygdala, and medial cortex. Conclusions. We found no difference in neuroinflammation measured by PET-TSPO between patients with rCI and rNC. However, we speculate that the strong correlation between TSPO uptake and BOLD-fMRI activation in brain regions involved in memory and known to have high androgen-receptor expression mediating plasticity (hippocampus and amygdala) might reflect inflammatory effects of ADT with compensatory upregulated/increased synaptic functions. Further studies of this imaging readout are warranted to investigate ADT-related CI.

Background. Genetic factors are one of the significant contributors to prostate cancer (PCa) development, and hereditary prostate cancer 2 (HPC2) locus gene ELAC2 is considered a PCa susceptibility region. The HPC2/ELAC2 gene has been identified by linkage analysis in familial prostate cancer patients in the United States but has never been studied in Burkina Faso. The objective of the present study was to analyze the carriage of the C650T (Ser217Leu) and G1621A (Ala541Thr) mutations of the ELAC2 gene and the risk factors in prostate cancer patients in Burkina Faso. Methods. This case-control study included 76 participants, including 38 histologically confirmed prostate cancer cases and 38 healthy controls without prostate abnormalities. PCR combined with restriction fragment length polymorphism (RFLP) was used to characterize the genotypes of the Ser217Leu and Ala541Thr polymorphisms of the ELAC2 gene. The correlations between the different genotypes and risk factors for prostate cancer were investigated. Results. The C650T mutation was present in 44.73% of prostate cancer cases and 47.37% of controls. The G1621A mutation was present in 26.32% of prostate cancer cases and 15.79% of controls. We did not detect an association between prostate cancer risk and the Ser217Leu () and Ala541Thr () variants of the ELAC2 gene. Also, the two ELAC2 SNPs did not correlate with clinical stage, prostate-specific antigen (PSA) level at diagnosis, or the Gleason score on biopsies. However, we found that 100% of homozygous carriers of the T650 mutation have an A1621 mutation (). Conclusion. Ser217Leu and Ala541Thr polymorphisms of ELAC2, considered alone or in combination, are not associated with prostate cancer risk.

Aim. Prostate cancer (PCa) is the second most common nonskin malignancy and the second most common cause of cancer-related deaths in men. The most common site of metastasis in PCa is the axial skeleton which may lead to back pain or pathological fractures. Hematogenous spread to the brain and involvement of the central nervous system (CNS) are a rare occurrence. However, failed androgen deprivation therapy (ADT) may facilitate such a spread resulting in an advanced metastatic stage of PCa, which carries a poor prognosis. Methods. In this systematic review, we searched the PubMed, Scopus, and Web of Science online databases based on the PRISMA guideline and used all the medical subject headings (MeSH) in terms of the following search line: (“Brain Neoplasms” OR “Central Nervous System Neoplasms”) and (“Prostatic Neoplasms” OR “Prostate”). Related studies were identified and reviewed. Results. A total of 59 eligible studies (902 patients) were included in this systematic review. In order to gain a deeper understanding, we extracted and presented the data from included articles based on clinical manifestations, diagnostic methods, therapeutic approaches, and prognostic status of PCa patients having BMs. Conclusion. We have demonstrated the current knowledge regarding the mechanism, clinical manifestations, diagnostic methods, therapeutic approaches, and prognosis of BMs in PCa. These data shed more light on the way to help clinicians and physicians to understand, diagnose, and manage BMs in PCa patients better.